← 返回 Skills 市场
lenger666

Amazon Listing Factory

作者 lenger666 · GitHub ↗ · v0.1.5 · MIT-0
cross-platform ⚠ suspicious
417
总下载
1
收藏
2
当前安装
6
版本数
在 OpenClaw 中安装
/install amazon-listing-factory
功能描述
Generate complete Amazon listing drafts with title, bullets, image plan, prompts, and video script.
使用说明 (SKILL.md)

Amazon Listing Factory

Generate complete Amazon listing drafts with:

  • title
  • bullets
  • image plan
  • image prompts
  • video script

If image environment is configured, it can continue image generation automatically.

完整教程链接: https://my.feishu.cn/docx/DzpHdBjJdosX6Nx7CAMc9OY5nZf

推荐在飞书中使用 Slash 命令调用:

/amazon_listing_factory 生成listing:充电宝,美国站,突出便携、大容量、安全感,输出6张图

安装或更新 Skill 后,请先执行:

openclaw gateway restart

检查是否识别成功:

openclaw skills list | grep amazon

如果看到:

amazon-listing-factory

说明 Skill 已被 OpenClaw 正确识别。

本地测试:

bash ~/.openclaw/workspace/skills/amazon-listing-factory/run.sh "生成listing:充电宝,美国站,突出便携、大容量、安全感,输出6张图"

安全使用建议
This skill largely does what it says (uses an LLM to draft Amazon listings and can call image APIs), but it also probes local environment and terminal state to auto-detect Feishu recipients and may send images via a helper script. Before installing: 1) Review the code (modules/coze_generate_image.py and skill.py) yourself or with a colleague. 2) Don’t run it with your production API keys until you’re comfortable — use a limited or test key. 3) If you don’t need automatic image sending, remove/disable the modules/coze_generate_image.py or clear FEISHU/OPENCLAW env vars. 4) Be aware it will create a .env in the skill directory and write runtime.log there. 5) If you want higher assurance, run the skill in an isolated environment or container and monitor network calls to verify which external endpoints are contacted.
功能分析
Type: OpenClaw Skill Name: amazon-listing-factory Version: 0.1.5 The amazon-listing-factory skill bundle is designed to generate Amazon product listings and associated images using OpenAI-compatible APIs and Coze workflows. The code logic in skill.py and modules/coze_generate_image.py is consistent with the stated purpose, featuring robust input parsing and safety sanitization to prevent prohibited marketing phrases (e.g., 'Add to Cart'). While the skill interacts with the system via tmux to retrieve user session IDs for Feishu notifications, this is a documented pattern within the OpenClaw ecosystem for context recovery and does not show signs of malicious intent or unauthorized data exfiltration.
能力评估
Purpose & Capability
Name/description match the implementation: the skill calls an LLM-compatible API to generate listing drafts and includes an optional image-generation module that calls external image APIs. Requiring an LLM API key (LISTING_API_KEY / OPENAI_API_KEY) and optional image keys (COZE_TOKEN / MIHE_KEY / COZE_WORKFLOW_ID) is coherent with the stated purpose.
Instruction Scope
SKILL.md is simple and claims only listing + optional image generation, but the code goes further: the image module attempts to detect a runtime recipient via many FEISHU-related env vars and also probes tmux's openclaw pane (runs 'tmux capture-pane') to extract sender/chat IDs. That behavior reads local terminal state and potentially chat metadata beyond what's described in the SKILL.md.
Install Mechanism
There is no install spec (instruction-only style plus code shipped). No remote downloads or archive extraction are performed by the skill itself. The skill will create a .env in its own directory if missing and write a runtime.log file — normal for a local tool but worth noting.
Credentials
The skill reads multiple API key env vars (LISTING_API_KEY, OPENAI_API_KEY, MOONSHOT_API_KEY, KIMI_API_KEY) and many FEISHU/OPENCLAW environment names to determine a recipient. Reading your LLM API key and optional image API keys is expected, but probing unrelated env names and collecting Feishu IDs increases the amount of sensitive data the skill can access and use to send outputs.
Persistence & Privilege
The skill does not request always:true and does not modify other skills. It writes a .env template into its own skill directory and appends to a runtime.log there. However it spawns subprocesses (tmux) and references a Feishu helper in TOOLBOX_ROOT, which could access other local tooling; these are not permanent privileges but are system interactions beyond simple LLM calls.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install amazon-listing-factory
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /amazon-listing-factory 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.5
加入了完整教程链接,不会安装使用的请点击飞书文档查看
v0.1.4
v0.1.4 Major Fix - 修复商店安装后 Skill 识别与调用说明不清晰的问题 New - 新增首次运行引导提示 - 新增 Slash 命令调用示例 /amazon_listing_factory - 新增安装后必须执行 openclaw gateway restart 的提示 Improvement - 保留原有可用生成逻辑,不改核心 skill.py 生成链路 - 优化 run.sh 无参数提示 - 优化 ENV_TEMPLATE.txt 模板 Docs - 更新 SKILL.md - 更新 README / QUICK_START / HOW_TO_USE - 明确 skills list 检查命令与飞书调用方式
v0.1.3
v0.1.3 Major Fix - 修复商店安装后 Skill 未被 OpenClaw 正确识别的问题 New - 新增首次运行引导提示 - 新增未配置图片环境时的明确提示 - 新增 Slash 命令调用示例 /amazon_listing_factory Improvement - 自动创建 listings 输出目录 - 优化无参数运行提示 - 优化图片环境检测和 fallback 文案 Docs - 更新 SKILL.md,明确 gateway restart、skills list 检查与飞书调用方式
v0.1.2
- Improved suggested input examples with more specific product details for clarity. - Added guidance that running without parameters now returns usage examples for easier onboarding. - Updated command and naming to use hyphens (amazon-listing-factory). - Clarified that the store version includes the image module by default—no need to install coze_generate_image.
v0.1.1
Improved first-run setup: the skill now auto-creates a .env template on first run and provides clearer configuration guidance when model settings are missing.
v0.1.0
Initial release: generate Amazon listing drafts with title, bullets, image plan, image prompts, and video script. Optional automatic image generation when image workflow is configured.
元数据
Slug amazon-listing-factory
版本 0.1.5
许可证 MIT-0
累计安装 2
当前安装数 2
历史版本数 6
常见问题

Amazon Listing Factory 是什么?

Generate complete Amazon listing drafts with title, bullets, image plan, prompts, and video script. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 417 次。

如何安装 Amazon Listing Factory?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install amazon-listing-factory」即可一键安装,无需额外配置。

Amazon Listing Factory 是免费的吗?

是的,Amazon Listing Factory 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Amazon Listing Factory 支持哪些平台?

Amazon Listing Factory 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Amazon Listing Factory?

由 lenger666(@lenger666)开发并维护,当前版本 v0.1.5。

💬 留言讨论